Distributed DNN Inference With Fine-Grained Model Partitioning in Mobile Edge Computing Networks

计算机科学 异步通信 推论 分布式计算 边缘设备 服务器 移动设备 边缘计算 GSM演进的增强数据速率 移动边缘计算 块(置换群论) 任务(项目管理) 计算机网络 人工智能 云计算 几何学 数学 管理 经济 操作系统
作者
Hui Li,Xiuhua Li,Qilin Fan,Qiang He,Xiaofei Wang,Victor C. M. Leung
出处
期刊:IEEE Transactions on Mobile Computing [IEEE Computer Society]
卷期号:23 (10): 9060-9074 被引量:7
标识
DOI:10.1109/tmc.2024.3357874
摘要

Model partitioning is a promising technique for improving the efficiency of distributed inference by executing partial deep neural network (DNN) models on edge servers (ESs) or Internet-of-Things (IoT) devices. However, due to heterogeneous resources of ESs and IoT devices in mobile edge computing (MEC) networks, it is non-trivial to guarantee the DNN inference speed to satisfy specific delay constraints. Meanwhile, many existing DNN models have a deep and complex architecture with numerous DNN blocks, which leads to a huge search space for fine-grained model partitioning. To address these challenges, we investigate distributed DNN inference with fine-grained model partitioning, with collaborations between ESs and IoT devices. We formulate the problem and propose a multi-task learning based asynchronous advantage actor-critic approach to find a competitive model partitioning policy that reduces DNN inference delay. Specifically, we combine the shared layers of actor-network and critic-network via soft parameter sharing, and expand the output layer into multiple branches to determine the model partitioning policy for each DNN block individually. Experiment results demonstrate that the proposed approach outperforms state-of-the-art approaches by reducing total inference delay, edge inference delay and local inference delay by an average of 4.76%, 10.04% and 8.03% in the considered MEC networks.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
1秒前
Stroeve发布了新的文献求助10
2秒前
欧阳月空完成签到,获得积分10
2秒前
2秒前
星辰大海应助李小宁采纳,获得10
3秒前
段一帆发布了新的文献求助10
3秒前
冷艳的姿发布了新的文献求助10
3秒前
4秒前
FIN应助小小采纳,获得30
4秒前
领导范儿应助su采纳,获得10
5秒前
Candy发布了新的文献求助10
5秒前
Rondab应助xiaosu采纳,获得10
6秒前
CodeCraft应助LJJ采纳,获得10
7秒前
7秒前
SYLH应助科研通管家采纳,获得20
8秒前
所所应助科研通管家采纳,获得10
8秒前
科研通AI5应助科研通管家采纳,获得10
8秒前
张金蝶完成签到,获得积分10
8秒前
搜集达人应助科研通管家采纳,获得10
9秒前
CAOHOU应助科研通管家采纳,获得10
9秒前
丘比特应助科研通管家采纳,获得10
9秒前
CAOHOU应助科研通管家采纳,获得10
9秒前
赘婿应助科研通管家采纳,获得10
9秒前
量子星尘发布了新的文献求助30
9秒前
SYLH应助科研通管家采纳,获得20
9秒前
9秒前
9秒前
9秒前
CAOHOU应助科研通管家采纳,获得10
9秒前
Lyuhng+1完成签到 ,获得积分10
10秒前
大个应助十九岁的时差采纳,获得10
11秒前
14秒前
桃花落完成签到,获得积分10
17秒前
su发布了新的文献求助10
17秒前
思源应助汪汪采纳,获得10
17秒前
高兴的天蓝完成签到 ,获得积分10
18秒前
18秒前
19秒前
星星应助momo采纳,获得10
19秒前
20秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
‘Unruly’ Children: Historical Fieldnotes and Learning Morality in a Taiwan Village (New Departures in Anthropology) 400
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
基于可调谐半导体激光吸收光谱技术泄漏气体检测系统的研究 350
Robot-supported joining of reinforcement textiles with one-sided sewing heads 320
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3989334
求助须知:如何正确求助?哪些是违规求助? 3531428
关于积分的说明 11253936
捐赠科研通 3270119
什么是DOI,文献DOI怎么找? 1804887
邀请新用户注册赠送积分活动 882087
科研通“疑难数据库(出版商)”最低求助积分说明 809173